dx-standards-discover
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it ingests and processes untrusted data from the local codebase and project documentation.
- Ingestion points: Processes linter/formatter configs, CI workflows, build scripts,
READMEfiles, and recurring code patterns across the project. - Boundary markers: The instructions lack explicit boundary markers or directives to disregard potential instructions embedded within the analyzed project files.
- Capability inventory: Performs file reads (various project configs and source code), invokes subagents (
Explore), and writes documentation to thecontext/standards/directory. - Sanitization: There is no evidence of sanitizing or validating the mined content before it is incorporated into the final prescriptive standards files.
Audit Metadata